Security audit

Code Review

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed code-review checklist skill with no executable payload, persistence, or hidden data movement.

Installers should treat this as a normal code-review aid. Because it grants Bash for optional audits and profiling, review any command before execution and consider pinning npx package versions when using the performance checklist.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (7)

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The trigger phrases are broad enough to activate on ordinary user requests like 'review this' or 'code review', which can cause this skill to run unexpectedly and influence agent behavior outside the user's precise intent. In a skill that imposes strong review workflows, unintended activation can override or derail other tasks, creating prompt-routing and context-collision risk rather than a direct code-execution flaw.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The Chinese trigger examples are similarly broad and lack guardrails, so common phrases like '审查代码' or '审查这个 PR' may activate the skill in situations where the user did not intend to invoke this specific review workflow. Because this is an agent skill designed to take over review behavior, multilingual broad triggers increase accidental invocation surface across more conversations.

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The trigger list includes broad everyday phrases like "review this" and "code review," which can cause the skill to activate in contexts the user did not clearly intend. Over-broad activation increases the chance of prompt hijacking or inappropriate routing, especially because this skill prescribes a strong review workflow and output format that could override a more specific user request.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 70% confidence
Finding: npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 70% confidence
Finding: npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Natural-Language Policy Violations

Low

Confidence: 87% confidence
Finding: The document consistently presents instructions in English and Chinese, implying a fixed locale/language format rather than offering a user-selected language preference. Under the language/locale policy, forcing a specific language presentation without opt-in can be a policy concern unless justified or optional.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: The document title and introductory text are presented in both English and Chinese throughout, indicating a fixed language/locale choice in the skill content. The file does not state that this bilingual requirement is optional, user-selectable, or justified by a region-specific use case, which can violate language/locale policy expectations.

Static analysis

No suspicious patterns detected.